INDEX

Explanations

phrases related to mobile device features and releases

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abi

-0.16

urus

-0.15

SWG

-0.15

arios

-0.14

unan

-0.14

 amongst

-0.14

ä»²

-0.14

!:

-0.14

berger

-0.14

á»ĳi

-0.13

POSITIVE LOGITS

Me

0.15

||||

0.15

 segment

0.14

 kraj

0.14

cod

0.14

MST

0.14

AINS

0.14

 country

0.14

	explicit

0.14

ekler

0.14

Activations Density 0.021%

phrases related to mobile device features and releases

No Comments

No Known Activations